© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 5986
    Prev
    Next
    INDEX
    Explanations

    mentions of specific brands

    oai_token-act-pair · gpt-3.5-turbo

    punctuations, specifically commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquette
    -0.80
    ertodd
    -0.69
    oing
    -0.67
    irie
    -0.67
    ideshow
    -0.67
    acters
    -0.65
    sein
    -0.65
    untarily
    -0.65
     0004
    -0.64
    robe
    -0.64
    POSITIVE LOGITS
     whose
    1.54
     which
    1.42
    whose
    1.37
     where
    1.30
     wherein
    1.30
     whom
    1.23
    which
    1.23
     whereby
    1.20
     who
    1.18
     whence
    1.09
    Activations Density 0.353%

    No Known Activations